Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms that indicate a significant impact or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acy
    -0.16
     Rosenstein
    -0.15
    hl
    -0.15
    hir
    -0.15
    åĤ¨
    -0.15
    rens
    -0.14
     Drum
    -0.14
    deer
    -0.14
    achat
    -0.14
    inement
    -0.14
    POSITIVE LOGITS
    carbon
    0.16
     clap
    0.15
    leo
    0.15
     Winter
    0.14
    ousel
    0.14
    aiser
    0.14
    _pal
    0.14
    alet
    0.14
     carbon
    0.14
    204
    0.14
    Act Density 0.025%

    No Known Activations